Omnivision Technologies, Inc.

Guansong Liu

Jizhang Shan

Chin Poh Pang

Wenshou Chen

Yiyi Ren

Lu Chang

Xiaodong Yang

Zhongyang Huang

Hongjun Li

Xinting Gao

Shimiao Li

Shan Xu

Peng Lin

Alireza Bonakdar

Lu Gao

Boyang Zhang

Da Meng

Boyd Fowler

Donghui Wu

Ramakrishna Kakarala

Jin Li

Daniel L Flamm

Chengming Liu

Ying Zhou

Hui Pan

Badrinath Padmanabhan

Richard Mann

Ye Tao

Yongshen Ni

Bin Chen

Yanfang Huang

Jess Jan Young Lee

Chengjun Li

Badri Padmanabhan

Ruijiang Luo

Yan Ye

Wenchao Zhang

Gao Lu

Shan Jizhang

Li Hongiun

A method of detecting an object in an image includes (i) processing, with a machine-learned model, pixel intensities of a pixel pair in a first region of the image, to determine a first confidence score representing a likelihood of the object being present within the first region, and (ii) determining, based on the first confidence score, presence of the object in the first region.

System and method for detecting an object within an image

An image processing method and a device configured to implement the same are disclosed. The method comprises: from an imaging device, obtaining image data that comprises temporally consecutive image frames; performing feature extraction on each of the obtained image frames; dynamically retaining extracted feature data of the obtained image frames in a feature accumulation database by regulating data retention in the feature accumulation database to a selective subset of the extracted feature data from the obtained image frames; performing Random Sample Consensus (RANSAC) operation on the selective subset of the extracted feature data from the feature accumulation database; and generating an estimation model from output of the RANSAC operation based on at least one of an extracted feature data of a current image frame or extracted feature data of one or more temporally preceding image frames of the obtained image frames.

Image processing method and apparatus implementing the same

An image processing method and a device configured to implement the same are disclosed. The device comprises: a hybrid imaging device configured to obtain optical input; and a processing device in signal communication with the hybrid imaging device. The processing device comprises: a motion detection circuit that performs feature tracking based on a first component of an obtained optical input; a motion estimation circuit that performs motion compensation based on output of the motion detection unit; a frame reconstruction circuit that reconstructs image frame based on both the output of the motion estimation unit and a second component of the optical input; and an output unit that outputs image frame at a predetermined global frame rate.

Hybrid dynamic vision sensor and CMOS device for motion compensation

A method and apparatus for embedding a digital watermark in image content that is not visible to the human eye is performed on single-sensor digital camera images (often called 'raw' images) from a pixel-array. The raw image is transformed to generate preprocessed image coefficients, a watermark message is encrypted using a first key; the encrypted watermark message is randomized using a second key to form a watermark; and the watermark is embedded in randomly selected preprocessed image coefficients.

Sensor watermarking on raw images

In some embodiments, an image sensor is provided. The image sensor comprises a plurality of photodiodes arranged as a photodiode array. The photodiodes of the photodiode array are arranged into a first quadrant, a second quadrant, a third quadrant, and a fourth quadrant. A first polarization filter and a first telecentric lens are aligned with the first quadrant. A second polarization filter and a second telecentric lens are aligned with the second quadrant. A third polarization filter and a third telecentric lens are aligned with the third quadrant. A fourth telecentric lens is aligned with the fourth quadrant.

Techniques for measuring depth and polarization from a single sensor

An image sensor processor implemented method for retaining pixel intensity, comprising: receiving, by the image processor, a numerical value indicative of a corresponding pixel intensity; determining, by the image processor, whether a least significant portion of the received numerical value is equal to a predetermined numerical value; and responsive to determining the least significant portion of the received numerical value is equal to the predetermined numerical value, rounding, by the image processor, the received numerical value of the corresponding pixel intensity to a higher or lower value depending on a bit sequence, and if the least significant portion of the received numerical value is not equal to the predetermined value, rounding the received numerical value to the higher or lower value based on the received numerical value; and binning the rounded value.

System and method for maintaining pixel intensity when rounding

The present application discloses an imaging system for detecting human-object interaction and a method for detecting human-object interaction thereof. The imaging system includes an event sensor, an image sensor, and a controller. The event sensor is configured obtain an event data set of the targeted scene according to variations of light intensity sensed by pixels of the event sensor when an event occurs in the targeted scene. The image sensor is configured capture a visual image of the targeted scene. The controller is configured to detect human according to the event data set, trigger the image sensor to capture the visual image when the human is detected, and detect the human-object interaction in the targeted scene according to the visual image and a series of event data sets obtained by the event sensor during the event.

Imaging system for detecting human-object interaction and a method for detecting human-object interaction

An image sensor pixel comprises a subpixel and a polarization pixel. The subpixel includes a group of photodiodes disposed in semiconductor material, a shared microlens optically aligned over the group of photodiodes, and a subpixel color filter disposed between the group of photodiodes and the shared microlens. The polarization pixel includes a first photodiode disposed in the semiconductor material, an unshared microlens optically aligned over the first photodiode, and a polarization filter disposed between the first photodiode and the unshared microlens. The shared microlens has a first lateral area. The unshared microlens has a second lateral area less than the first lateral area of the shared microlens.

Image sensor with shared microlens and polarization pixel

An image sensor pixel includes a plurality of photodiodes, a shared microlens, and a plurality of microlenses. The plurality of photodiodes are arranged as a photodiode array with each of the plurality of photodiodes disposed within a semiconductor material. The shared microlens is optically aligned with a group of neighboring photodiodes included in the plurality of photodiodes. Each of the plurality of microlenses are optically aligned with an individual one of the plurality of photodiodes other than the group of neighboring photodiodes. The plurality of microlenses laterally surrounds the shared microlens.

Image sensor with shared microlens between multiple subpixels

An image sensor includes a plurality of photodiodes, a plurality of color filters, and a plurality of microlenses. The plurality of photodiodes are arranged as a photodiode array, each of the plurality of photodiodes disposed within respective portions of a semiconductor material with a first lateral area. The plurality of color filters are arranged as a color filter array optically aligned with the photodiode array. Each of the plurality of color filters having a second lateral area greater than the first lateral area. The plurality of microlenses are arranged as a microlens array optically aligned with the color filter array and the photodiode array. Each of the plurality of microlenses have a third later area greater than the first lateral area and less than the second lateral area.

Image sensor with shared microlens

In some embodiments, an image sensor is provided. The image sensor comprises a plurality of photodiodes arranged as a photodiode array. The plurality of photodiodes includes a first set of photodiodes configured as phase detection photodiodes, and a second set of photodiodes configured as polarization detection photodiodes. In some embodiments, a controller is provided. The controller comprises circuitry configured to process signals from a first set of photodiodes of a photodiode array to obtain depth information; process signals from a second set of photodiodes of the photodiode array to obtain polarization information; process the polarization information to obtain an ambiguous set of surface normals; and process the ambiguous set of surface normals using the depth information to obtain a three-dimensional shape image.

Devices and methods for obtaining three-dimensional shape information using polarization and phase detection photodiodes

A chart for calibrating a system of multiple cameras, the chart comprising: a background; an array of dots contrasting the background, wherein the array of dots are arranged in rows and columns, wherein the array of dots comprise a first dot array, and a second dot array, wherein the first dot array fully occupies a first region of evenly spaced dots with a first dot density, the second dot array fully occupies a second region of evenly spaced dots with a second dot density, and wherein the second region is enclosed within the first region; a group of first markers in the first region, a group of second markers in the second region, and a third marker at the center of the chart, wherein each second marker is closer to the third marker than each first marker.

Multiple camera calibration chart

A multiple camera imaging system comprises a first camera image sensor to obtain a first image of a scene and a second camera image sensor to obtain a second image. The system further comprises an image signal processor (ISP) to produce a first roughly-aligned image from the first image and a second roughly-aligned image from the second image. A feature point in the first roughly-aligned image is identified. A center of a search zone is created, which is a combination of the position of the feature point and an associated disparity value from the first and second roughly-aligned images. The search zone is created within the second roughly-aligned image. Candidate feature points are identified within the search zone, which is much smaller than the entire image. A best-matched feature point pair in the first roughly-aligned image and the second roughly-aligned image is then identified.

Aligning two images by matching their feature points

A multiple camera imaging system, comprising a first camera image sensor configured to obtain a first image of a scene from a first vantage perspective point; a second camera image sensor configured to obtain a second image of the scene from a second vantage perspective point; and an image signal processor (ISP), configured to process the first image and the second image by performing the following steps: producing a first monotone image from the first image, and a second monotone image from the second image; projecting the first monotone image to produce a first one-dimensional profile; and projecting the second monotone image to produce a second one-dimensional profile; extracting a matching information from the first and second one-dimensional profiles by matching the second one-dimensional profile to the first one dimensional profile; using the matching information produce a first processed two-dimensional image, and a second processed two-dimensional image that is aligned with the first processed two-dimensional image.

Alignment of multiple camera images by matching projected one dimensional image profiles

A method for processing a plurality of images of a scene recorded from different vantage points, where the plurality of images includes a color reference image captured by a Bayer type camera and at least one additional image, the method including (a) registering at least a portion of the plurality of images, and (b) generating a unitary color image from the plurality of images, wherein color information of the unitary color image is determined exclusively from the color reference image.

Growing community of inventors

San Jose, CA, United States of America

Guansong Liu